Noise reduction

MTDiff: A Multi-Task Diffusion Accelerator With Bandwidth-Aware Memory Partition and Efficient Digital Compute-in-Memory

MTDiff: A Multi-Task Diffusion Accelerator With Bandwidth-Aware Memory Partition and Efficient Digital Compute-in-Memory 150 150

Abstract:

Initially applied to image synthesis, diffusion models have rapidly expanded into various content generation tasks, such as 3-D scene reconstruction and video generation, due to the superior generative quality. Based on our observations, the imbalanced operational intensities across diffusion model layers lead to suboptimal hardware utilization due to inadequate bandwidth …

View on IEEE Xplore

A 92.1-dB SNDR Easy-Driving Two-Step NS-SAR-Based Incremental ADC With Concurrent Gain-Error Plus Noise Suppression

A 92.1-dB SNDR Easy-Driving Two-Step NS-SAR-Based Incremental ADC With Concurrent Gain-Error Plus Noise Suppression 150 150

Abstract:

This article presents a two-step incremental analog-to-digital converter (ADC) that achieves high resolution and energy efficiency while substantially easing the input driving constraints and interstage gain variation. By employing a level-shifted sub-ranging architecture with an input-tracking (IT) feature, the design obviates direct input sampling, thereby significantly relaxing the demands on …

View on IEEE Xplore

BASS-PLL: A Bandwidth Augmented Sub-Sampling PLL Achieving a Wide Bandwidth Above 30% of the Reference Frequency and a Worst Case FoMREF of −247.9 dB at 3 GHz With a Ring Oscillator

BASS-PLL: A Bandwidth Augmented Sub-Sampling PLL Achieving a Wide Bandwidth Above 30% of the Reference Frequency and a Worst Case FoMREF of −247.9 dB at 3 GHz With a Ring Oscillator 150 150

Abstract:

This work presents a bandwidth augmented sub-sampling phase-locked loop (BASS-PLL) architecture that features simultaneous out-of-band noise suppression by direct and multipath sampling of the ring oscillator’s (ROs) output and in-band noise suppression via an intrinsic sub-sampling mechanism, ultimately combining the benefits of over-sampling PLLs (OS-PLLs) and sub-sampling PLLs (SS-PLLs) …

View on IEEE Xplore

A 11.0-TOPS/W Diffusion Accelerator With Temporal Data Reuse for Real-Time Text-to-Motion Generation

A 11.0-TOPS/W Diffusion Accelerator With Temporal Data Reuse for Real-Time Text-to-Motion Generation 150 150

Abstract:

Text-to-motion models are AI systems that generate human motion sequences directly from natural language descriptions, serving as key enablers for immersive virtual avatars and interactive digital humans in AR/VR ecosystems. However, state-of-the-art text-to-motion diffusion models suffer from substantial computational costs due to their iterative nature, making them ill-suited for …

View on IEEE Xplore

0.13 K NETD D-Band CMOS Passive Imager With Noise Suppression Analysis

0.13 K NETD D-Band CMOS Passive Imager With Noise Suppression Analysis 150 150

Abstract:

This article presents a new system design and in-depth analysis of a wideband, low-power passive imaging receiver based on a Dicke-switch architecture, implemented in 28 nm CMOS technology. The proposed structure employs a three-coil gm-boosting technique for the low-noise amplifier (LNA). This approach reduces the LNA’s noise figure (NF) and …

View on IEEE Xplore

A 57.3-fps 12.8 TFLOPS/W Text-to-Motion Processor With Inter-Iteration Output Sparsity and Inter-Frame Joint Similarity

A 57.3-fps 12.8 TFLOPS/W Text-to-Motion Processor With Inter-Iteration Output Sparsity and Inter-Frame Joint Similarity 150 150

Abstract:

Recently, 3-D human motion generation has become essential in media applications such as film production and augmented reality (AR)/virtual reality (VR) devices, requiring the generation of human joint movements and detailed 3-D meshes for each joint. Traditionally, joint creation required hours or even days, making it impractical for real-time …

View on IEEE Xplore